Depth Separation with Multilayer Mean-Field Networks

04/03/2023

∙

by   Yunwei Ren, et al.

∙

0

∙

share

Depth separation – why a deeper network is more powerful than a shallower one – has been a major problem in deep learning theory. Previous results often focus on representation power. For example, arXiv:1904.06984 constructed a function that is easy to approximate using a 3-layer network but not approximable by any 2-layer network. In this paper, we show that this separation is in fact algorithmic: one can learn the function constructed by arXiv:1904.06984 using an overparameterized network with polynomially many neurons efficiently. Our result relies on a new way of extending the mean-field limit to multilayer networks, and a decomposition of loss that factors out the error introduced by the discretization of infinite-width mean-field networks.